基于在线最小二乘支持向量机回归的电力系统暂态稳定预测.pdfVIP

第27 卷 第25 期 中 国 电 机 工 程 学 报 Vol.27 No.25 Sep. 2007 2007 年9 月 Proceedings of the CSEE ©2007 Chin.Soc.for Elec.Eng. 0258-8013 (2007) 25-0038-06 TM74 A 470 40 文章编号： 中图分类号： 文献标识码： 学科分类号： ⋅ 基于最小二乘支持向量机的电力系统 暂态稳定在线预测 吴 琼，杨以涵，刘文颖 (华北电力大学电力系统保护与动态安全监控教育部重点实验室，北京市 昌平区 102206) Electric Power System Transient Stability On-line Prediction Based on Least Squares Support Vector Machine WU Qiong, YANG Yi-han, LIU Wen-ying (Key Laboratory of Power System Protection and Dynamic Security Monitory and Control under Ministry of Education, North China Electric Power University, Changping District, Beijing 102206, China) ABSTRACT: In prediction of the power system transient 0 引言 trajectory with least squares support vector machine (LS-SVM), 暂态稳定性破坏是大电网中常见的稳定性事 repeatedly inverting matrix is the most important factor in 故，寻求快速、准确的暂态稳定预测方法具有重要 calculation speed. According to the theorem of inverting block matrix, this paper modified the algorithm to save calculation 意义。近年来，随着广域测量系统(WAMS)的发展， time. In order to satisfy the requirement for on-line transient 控制中心可以足够的精度和速度获得反映系统动 stability prediction of multi-machine system, the trajectories 态行为的同步数据，为实现基于受扰轨迹的暂态稳 [1] polymerization technology was used to reduce computing 定预测提供了新契机 。广大研究人员提出了多种 complexity. Based on extended equal area criterion (EEAC), 暂态稳定预测方法，可分为模型化方法和非模型化